← Back to People
A research scientist at FAIR CodeGen Team, Meta Superintelligence Labs who works on improving agentic coding capabilities for Meta's next-generation LLM.
1
Mentions
1
Articles
1
Outlets
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Yue Yu
Article Types
- research1
Media Angles
- technical1
Narrative Framing
- breakthrough1
Associated AI Models
Qwen3-30B-A3B1
Articles
Most recent firstMentioned In
Referenced in coverage
Training AI Co-Scientists Using Rubric Rewards
Meta Superintelligence LabsresearchpositiveJan 4, 2026
Meta demonstrates that language models can be trained to generate better scientific research plans using reinforcement learning with self-grading rubrics extracted from existing papers, achieving 70% expert preference improvements and cross-domain generalization to medical research.
“Co-authored research on training AI co-scientists using rubric rewards.”
AI ResearchReinforcement LearningFoundation ModelsAI Agents